I’ll spend a few minutes discussing the paper that a few of us were mumbling about last week that uses the pyramid histogram kernel to model spatial relationships.
I’ll spend the bulk of the time discussing the paper:
Hyperfeatures — Multilevel Local Coding for Visual Recognition
by Ankur Agarwal and Bill Triggs.
It’s been accepted as an oral for ECCV 2006. The tech report relating to the paper is here. The conference submission will be made available via email, but should not be distributed, as requested by the author.